© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117168
    Prev
    Next
    INDEX
    Explanations

    inducing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     каждую
    -0.07
    每
    -0.07
     еже
    -0.07
     એક
    -0.06
     requested
    -0.06
     ou
    -0.06
     एक
    -0.06
    一個
    -0.06
    still
    -0.06
     请求
    -0.06
    POSITIVE LOGITS
     it
    0.07
     teilen
    0.06
     obecnie
    0.06
     jednocześnie
    0.06
    ွေ
    0.06
     одновременно
    0.06
     commend
    0.06
     Remarkably
    0.06
    Remark
    0.06
     notably
    0.06
    Activations Density 0.001%

    No Known Activations